Towards coordinated and robust real-time control: a decentralized approach for combined sewer overflow and urban flooding reduction based on multi-agent reinforcement learning

• Published in: Water research (Oxford) 2023-02, Vol.229, p.119498-119498, Article 119498
• Main Authors: Zhang, Zhiyu, Tian, Wenchong, Liao, Zhenliang
• Format: Article
• Language: English
• Subjects: Combined sewer overflow; Decentralized real-time control; Floods; Models, Theoretical; Multi-agent reinforcement learning; Urban drainage system
• ISSN: 0043-1354; 1879-2448
• DOI: 10.1016/j.watres.2022.119498

•Real-time control of two drainage systems based on multi-agent reinforcement learning.•The proposed strategies can reduce combined sewer overflow and urban flooding.•Decentralized structure enhances robustness against communication failure. The real-time control (RTC) of urban drainage systems can make full use of the capabilities of existing infrastructures to mitigate combined sewer overflow (CSO) and urban flooding. Despite the benefits of RTC, it may encounter potential risks and failures, which need further consideration to enhance its robustness. Besides failures of hardware components such as sensors and actuators, the RTC performance is also sensitive to communication failures between the devices that are spatially distributed in a catchment-scale system. This paper proposes a decentralized control strategy based on multi-agent reinforcement learning to enhance communication robustness and coordinate the decentralized control agents through centralized training. To investigate different control structures, a centralized and a fully decentralized strategy are also developed based on reinforcement learning (RL) for comparison. A benchmark drainage model and a real-world drainage model are formulated as two cases, and the control agents are trained to control the orifices or pumps for CSO or flooding mitigation in each case. The three RL strategies reduce the CSO volume by 5.62-9.30% compared with a static baseline in historical rainfalls of the benchmark case and reduce the CSO and flooding volume by 14.39-21.36% compared with currently-used rule-based control in synthetic rainfalls of the real-world case. Benefitting from centralized training, the decentralized agents can achieve similar performance to the centralized agent. The decentralized control also enhances the communication robustness with smaller performance loss than the centralized control when observation communication fails, and provides a robust backup at the local level to limit the uncertainties when action commands from the centralized agent are lost. The results and findings indicate that multi-agent RL contributes to a coordinated and robust solution for RTC of urban drainage systems. [Display omitted]